Research on black spot identification of safety in urban traffic accidents based on machine learning method

Fan, Zhanyong; Li, Chun; Cai, Dongjian; Yue, Shun

doi:10.1016/j.ssci.2019.05.039

Cited by 60 publications

(38 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results of the comparison of the two methods are stated to be more accurate, but no precise accuracy value is given based on the value of the confusion matrix [35]. On research [36] have not considered the type of road type design, for example, arterial roads, collector roads, or roads based on their nature (geometric road), there are no studies on adaptive models that can expand machine learning through a combination of online learning and deep learning [37]. Paper discussion [38] is still limited to the use of an existing method; knowledge combination has not been done as a hybrid model approach.…”

Section: Methodsmentioning

confidence: 99%

Spatial analysis model for traffic accident-prone roads classification: a proposed framework

Vitianingsih

Suryana

Othman

2021

IJ-AI

View full text Add to dashboard Cite

<span id="docs-internal-guid-9754d3d8-7fff-a7d2-6605-1c8f8c5a707a"><span>The classification method in the spatial analysis modeling based on the multi-criteria parameter is currently widely used to manage geographic information systems (GIS) software engineering. The accuracy of the proposed model will play an essential role in the successful software development of GIS. This is related to the nature of GIS used for mapping through spatial analysis. This paper aims to propose a framework of spatial analysis using a hybrid estimation model-based on a combination of multi-criteria decision-making (MCDM) and artificial neural networks (ANNs) (MCDM-ANNs) classification. The proposed framework is based on the comparison of existing frameworks through the concept of a literature review. The model in the proposed framework will be used for future work on the traffic accident-prone road classification through testing with a private or public spatial dataset. Model validation testing on the proposed framework uses metaheuristic optimization techniques. Policymakers can use the results of the model on the proposed framework for initial planning developing GIS software engineering through spatial analysis models.</span></span>

show abstract

Section: Methodsmentioning

confidence: 99%

Spatial analysis model for traffic accident-prone roads classification: a proposed framework

Vitianingsih

Suryana

Othman

2021

IJ-AI

View full text Add to dashboard Cite

show abstract

“…In addition, various machine learning methods and spatial regression models have been increasingly used in traffic accident research due to their capacity for superfitting to nonlinear problems. Among them, support vector machine (SVM) methods use kernel functions for nonlinear classification [58][59][60]; hierarchical clustering algorithms divide traffic impacts into layers based on data distribution [61]; K-means clustering algorithms and GWR both perform cluster analysis based on the collection distance of sample points [62]; and deep learning is often applied to general graph models or hypergraph models without massive constraints [62], such as image recognition of traffic accidents in social media and black spot recognition in urban traffic safety [63][64][65]. However, the earlier studies present a lack of accuracy due to the errors and unobserved variances.…”

Section: Methodological Reviewmentioning

confidence: 99%

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Yang

Chung

Kim

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

In cities, road traffic accidents are critical endangerment to people’s safety. A vast number of studies which are designed to understand these accidents’ leading causes and mechanisms exist. The widely held view is that emerging analysis methods can be a critical tool for understanding the complex interactions between land use and urban transportation. Using a case study of Suzhou Industrial Park (SIP) in Suzhou, China, this paper examines the relationship between different land use types and traffic accidents using a gradient boosting model (GBM) machine learning method. The results show that the GBM can be used as an effective accident model for a variety of research and analysis methods by (1) ranking the influential factors, (2) testing the degree of interpretation of each variable as the complexity of iterations changes, and (3) obtaining partial dependence plots, among other methods. The findings of this study also suggest that land use types—including facility points—demonstrate differing degrees of influence at two geographical scales: local level and neighborhood level. In the ranking of relative importance at both scales, the variables of education institutions, traffic lights, and service institutions are all ranked high—with a more significant influence on the occurrence of accidents. However, residential land and land use mix variables differed significantly in both scales and showed a significant deviation compared to the other results. When adjusting the complexity of the decision tree, the local level is more suitable for measuring variables such as residential areas and green parks where pedestrians and vehicles have fixed mobility periods and moderate flows. On the contrary, the nearest neighborhood level is more suitable to a small number of variables related to public service facilities at fixed locations, such as traffic lights and bus stops. In the partial dependence plots, all variables, except educational institutions and residences, show a positive correlation for accidents in the fitting process. The results of this study can ideally help inform transportation planners to reconsider transport accident occurrence rates in the context of the proximity to various land use types and public service facilities.

show abstract

“…Many clustering and classification algorithms have been used for segmentation or group traffic accidents. Examples include, k-means [28,29], latent class clustering (LCC) [30], and SVM [31]. However, these methods perform like a 'black box' approach and it is difficult to explain the stratification outcome.…”

Section: Spatial Stratified Heterogeneity Detection Of Traffic Accidentsmentioning

confidence: 99%

Geographical Detection of Traffic Accidents Spatial Stratified Heterogeneity and Influence Factors

Zhang

2020

IJERPH

View full text Add to dashboard Cite

The purpose of this paper is to investigate the existence of stratification heterogeneity in traffic accidents in Shenzhen, what factors influence the casualties, and the interaction of those factors. Geographical detection methods are used for the analysis of traffic accidents in Shenzhen. Results show that spatial stratification heterogeneity does exist, and the influencing factors of fatalities and injuries are different. The traffic accident causes and types of primary responsible party have a strong impact on fatalities and injuries, followed by zones and time interval. However, road factors, lighting, topography, etc., only have a certain impact on fatalities. Drunk driving, speeding over 50%, and overloading are more likely to cause more casualties than other illegal behaviors. Speeding over 50% and speeding below 50% have significant different influences on fatalities, while the influences on injuries are not obvious, and so do drunk driving (Blood Alcohol Concentration ≥ 0.08) and driving under the influence of alcohol (0.08 > Blood Alcohol Concentration ≥ 0.02). Both pedestrians and cyclists violating the traffic law are vulnerable to fatality. Heavy truck overloading is more likely to cause major traffic accidents than minibuses. More importantly, there are nonlinear enhanced interactions between the influencing factors, the combination of previous non-significant factors and other factors can have a significant impact on the traffic accident casualties. The findings could be helpful for making differentiated prevention and control measures for traffic accidents in Shenzhen and the method selection of subsequent research.

show abstract

Research on black spot identification of safety in urban traffic accidents based on machine learning method

Cited by 60 publications

References 17 publications

Spatial analysis model for traffic accident-prone roads classification: a proposed framework

Spatial analysis model for traffic accident-prone roads classification: a proposed framework

Local or Neighborhood? Examining the Relationship between Traffic Accidents and Land Use Using a Gradient Boosting Machine Learning Method: The Case of Suzhou Industrial Park, China

Geographical Detection of Traffic Accidents Spatial Stratified Heterogeneity and Influence Factors

Contact Info

Product

Resources

About